International Journal of Engineering Research in Electronics and Communication Engineering(IJERECE)

Monthly Journal for Electronics and Communication Engineering

Volume4,December 2017,

Topic : Automatic Tuberculosis Detection Based On Multiple Instance Learning Classifiers from the X-Ray Images

Authors:Vallithai.C || Ahila

Abstract:The major advantage of multiple-instance learning (MIL) applied to a computer-aided detection (CAD) system is that it allows optimizing the latter with case-level labels instead of accurate lesion outlines as traditionally required for a supervised approach. In previous work, a MIL-based CAD system can perform comparably to its supervised counterpart considering complex tasks such as chest radiograph scoring in tuberculosis (TB) detection. However, despite this remarkable achievement, the uncertainty inherent to MIL can lead to a less satisfactory outcome if analysis at lower levels (e.g., regions or pixels) is needed. This issue may seriously compromise the applicability of MIL to tasks related to quantification or grading, or detection of highly localized lesions. In this project, we propose to reduce uncertainty by embedding a MIL classifier within an active learning (AL) framework. To minimize the labelling effort, we develop a novel instance selection mechanism that exploits the MIL problem definition through one-class classification. We adopt this mechanism to provide meaningful regions instead of individual instances for expert labelling, which a more appropriate strategy is given the application domain. In addition, and contrary to usual AL methods, a single iteration is performed. To show the effectiveness of our approach, we compare the output of a MIL-based CAD system trained with and without the proposed AL framework. The task is to detect textural abnormalities related to TB. Both quantitative and qualitative evaluations at the pixel level are carried out..

Keywords: Leakage detection, continuous object detection,wireless sensor networks

Download Paper


DOI: 01.1617/vol4/iss12/pid86019


Related Articles

Design and Implementation of nRF Based Smart Home System Using IoT

Authors: J.Krishna Chaithanya || Dr. T. Ramashri

Doi : 01.1617/vol4iss3pid024

Volume4 ,March 2017.

Real-Time Vehicle Tracking Using GSM & GPS with Location Display on Google Maps Using Raspberry Pi

Authors: J.Krishna Chaithanya || Dr. T. Ramashri

Doi : 01.1617/vol4iss3pid025

Volume4 ,March 2017.

Obstacle Avoiding Intelligent Robot

Authors: Prof.S. B. Mandlik || Miss.Kshirsagar Snehal D , Miss. Gaikwad Jyoti B , Miss.Wagh Varsha S , Miss. Ingale komal M

Doi : 01.1617/vol4iss3pid026

Volume4 ,March 2017.

Increased Learning In Retinal Blood Vessel Segmentation Approach Based on Fuzzy-C Means Clustering and Mathematical Morphology

Authors: Naluguru Udaya Kumar || Tirumala Ramashri

Doi : 01.1617/vol4iss3pid027

Volume4 ,March 2017.

A Review on Atmospheric Effects on Free Space Optical Link

Authors: Shaik.Taj Mahaboob || A.Sree Madhuri

Doi : 01.1617/vol4iss3pid028

Volume4 ,March 2017.

Efficient Medical Image Compression based on Region of Interest

Authors: S. Muni Rathnam || T. Ramashri

Doi : 01.1617/vol4iss3pid029

Volume4 ,March 2017.

CBIR Based Crack Detection System for Surface Traffic

Authors: Dr.Abraham Mathew || Dr.S. Saravanan, Dr. P. Mohanaiah

Doi : 01.1617/vol4iss3pid030

Volume4 ,March 2017.

IOT Based Digital Notice Board

Authors: K.Dinesh || M.Siva Ramakrishna

Doi : 01.1617/vol4iss3pid031

Volume4 ,March 2017.

Automatic Monitoring and Controlling of Greenhouse System using Zigbee

Authors: G. Hima Bindu || K. Lokesh Krishna , K. Hemalatha

Doi : 01.1617/vol4iss3pid032

Volume4 ,March 2017.

Hybrid Image Classification using ACO with Fuzzy Logic for Textured and Non-Textured Images

Authors: Subba Rao K || Dr. Sambasivarao N , Dr. Sammulal P

Doi : 01.1617/vol4iss3pid033

Volume4 ,March 2017.



Editor-in-Chief

Editor Image

Dr.Zhongfu Tan
National Professor,
North China Electric Power University,
CHINA


View more

IMPACT FACTOR: 3.689

ISSN(Online): 2394-6849

Google Scholar Profile

Thomson Reuters ID : q-6288-2016.
ORCiD Research ID : 0000-0001-9540-6799

All Issues


DOWNLOAD

Copy-Right Form Paper Template

ACCEPTANCE RATIO

ACCEPTANCE RATIO: 29.74%
ARTICLES PUBLISHED:0489
PAPER RECEIVED:01630
Journal Code : IJERECE
Electronic ISSN : 2394-6849
Impact Factor : 3.689
Frequency : monthly
Contact : info@ijerece.com

IFERP OTHER JOURNALS


Subscribe

           Email:

SOCIAL MEDIA